Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    rankings and finishing places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Working
    0.71
    Going
    0.71
    (
    0.70
    TH
    0.69
    DO
    0.68
    :
    0.68
    Go
    0.65
    My
    0.64
    OK
    0.64
    PHP
    0.63
    POSITIVE LOGITS
     కే
    0.70
    ।'
    0.69
     (\%)
    0.68
    ieves
    0.65
     prizes
    0.64
     대회
    0.64
     racers
    0.61
     уйна
    0.59
    entino
    0.59
     ప్
    0.59
    Act Density 0.022%

    No Known Activations